Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3638 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1229746 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1227. Min Act: -0.0001

Data Index: 919993 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1211. Min Act: -0.0001

Data Index: 982975 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1114035 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1214. Min Act: -0.0001

Data Index: 159723 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1159. Min Act: -0.0001

Data Index: 191139 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1159. Min Act: -0.0001

Data Index: 323657 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1256212 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1310732 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1164. Min Act: -0.0001

Data Index: 956788 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1134. Min Act: -0.0001

Data Index: 33691 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1357422 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1125. Min Act: -0.0001

Data Index: 80665 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1343383 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1218064 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1124. Min Act: -0.0001

Data Index: 613181 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1105. Min Act: -0.0001

Data Index: 266099 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1105. Min Act: -0.0001

Data Index: 859057 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1124. Min Act: -0.0001

Data Index: 81839 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1328980 (C4 (Web Text))

Max Activating Token Index: 760